改进多尺度卷积神经网络的单幅图像去雾方法
|
摘要
针对当前已有的去雾方法容易造成天空区域存在光晕以及色彩失真的现象,提出了一种多尺度卷积结合大气散射模型的单幅图像去雾算法。将原始有雾图像与三个不同尺度的卷积核进行卷积,经过一系列特征学习后得到粗略的传播图,然后使用引导滤波器对其进行优化,得到精细化后的传播图。利用粗传播图和有雾图像计算出全局大气光。根据大气散射模型反推出无雾清晰图像。实验结果表明,该方法对天空区域的处理更加自然,在图像的纹理细节以及颜色失真上有较好的效果。
As the current reported dehazing method is easy to cause halo and color distortion in the sky region, a single image dehazing algorithm by combining multi-scale convolution with scattering model is proposed. Firstly, the original haze image is convoluted with three different scales of convolution kernels. After a series of characteristic learning, the rough transmission is obtained. Then the transmission map is refined by using the guided filter. Secondly, according to the haze image and rough transmission, the global atmospheric light is known. Finally, with the refined transmission map and the calculated atmospheric light, the final dehazed image is inversely derived from the atmospheric scattering model.Experimental results show that the proposed algorithm is more natural to deal with the sky area, and it has better restoration effect on image texture and color distortion.
As the current reported dehazing method is easy to cause halo and color distortion in the sky region, a single image dehazing algorithm by combining multi-scale convolution with scattering model is proposed. Firstly, the original haze image is convoluted with three different scales of convolution kernels. After a series of characteristic learning, the rough transmission is obtained. Then the transmission map is refined by using the guided filter. Secondly, according to the haze image and rough transmission, the global atmospheric light is known. Finally, with the refined transmission map and the calculated atmospheric light, the final dehazed image is inversely derived from the atmospheric scattering model.Experimental results show that the proposed algorithm is more natural to deal with the sky area, and it has better restoration effect on image texture and color distortion.
引文
[1]Kim J Y,Kim L S,Hwang S H.An advanced contrast enhancement using partially overlapped sub-block histogram equalization[J].IEEE Transactions on Circuits&Systems for Video Technology,2001,11(4):475-484.
[2]Jang J H,Bae Y,Ra J B.Contrast-enhanced fusion of multi-sensor images using subband-decomposed multiscale retinex[J].IEEE Transactions on Image Processing,2012,21(8):3479-3490.
[3]Tarel J P,Hautière N.Fast visibility restoration from a single color or gray level image[C]//IEEE International Conference on Computer Vision,2010:2201-2208.
[4]Fattel R.Single image dehazing[J].ACM Transactions on Graphics,2008,27(3):721-728.
[5]Dong Xuemei,Hu Xiyuan,Peng Silong,et al.Single color image dehazing using sparse priors[C]//IEEE International Conference on Image Processing,2010:3593-3596.
[6]Zhu Qingsong,Mai Jiaming,Shao Ling.A fast single image haze removal algorithm using color attenuation prior[J].IEEE Transactions on Image Processing,2015,24(11):3522-3532.
[7]He K,Sun J,Tang X.Single image haze removal using dark channel prior[C]//IEEE Conference on Computer Vision and Pattern Recognition,2009:1956-1963.
[8]He K,Sun J,Tang X O,et al.Guided image filtering[C]//Proceedings of the 11th European Conference on Computer Vision,Heraklion,2010:1-14.
[9]苏晋鹏,陈恩俊,景嘉帅,等.基于阈值分割的暗原色先验图像去雾方法[J].计算机工程与应用,2017,53(3):205-210.
[10]Meng G,Wang Y,Duan J,et al.Efficient image dehazing with boundary constraint and contextual regularization[C]//IEEE International Conference on Computer Vision,2014:617-624.
[11]Tang K,Yang J,Wang J.Investigating haze-relevant features in a learning framework for image dehazing[C]//IEEE Conference on Computer Vision and Pattern Recognition,2014:2995-3002.
[12]麦嘉铭,王美华,梁云,等.特征学习的单幅图像去雾算法[J].中国图象图形学报,2016,21(4):464-474.
[13]Cai B,Xu X,Jia K,et al.DehazeNet:an end-to-end system for single image haze removal[J].IEEE Transactions on Image Processing,2016,25(11):5187-5198.
[14]Lin H Y,Lin C J.Using a hybrid of fuzzy theory and neural network filter for single image dehazing[J].Applied Intelligence,2017,47(4):1099-1114.
[15]Eigen D,Krishnan D,Fergus R.Restoring an image taken through a window covered with dirt or rain[C]//IEEE International Conference on Computer Vision,2013:633-640.
[16]刘万军,赵庆国.基于颜色饱和度的快速图像去雾研究[J].计算机工程与应用,2017,53(8):209-215.
[17]Nayar S K,Narasimhan S G.Vision in bad weather[C]//IEEE International Conference on Computer Vision,1999:820.
[18]李策,赵新宇,肖利梅,等.生成对抗映射网络下的图像多层感知去雾算法[J].计算机辅助设计与图形学学报,2017,29(10):1835-1843.
[19]Goodfellow I,Warde-farley D,Mirza M,et al.Maxout networks[C]//Proceedings of the 30th International Conference on Machine Learning,2013:1319-1327.
[20]Wu Y,Zhao H,Zhang L.Image denoising with rectified linear units[C]//International Conference on Neural Information Processing,Cham,2014:142-149.
[21]Wang W,Yuan X,Wu X,et al.Fast image dehazing method based on linear transformation[J].IEEE Transactions on Multimedia,2017,19(6):1142-1155.
[22]Scharstein D,Szeliski R.A taxonomy and evaluation of dense two-frame stereo correspondence algorithms[J].International Journal of Computer Vision,2002,47:7-42.
[23]Scharstein D,Szeliski R.High-accuracy stereo depth maps using structured light[C]//IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2003:195-202.
[2]Jang J H,Bae Y,Ra J B.Contrast-enhanced fusion of multi-sensor images using subband-decomposed multiscale retinex[J].IEEE Transactions on Image Processing,2012,21(8):3479-3490.
[3]Tarel J P,Hautière N.Fast visibility restoration from a single color or gray level image[C]//IEEE International Conference on Computer Vision,2010:2201-2208.
[4]Fattel R.Single image dehazing[J].ACM Transactions on Graphics,2008,27(3):721-728.
[5]Dong Xuemei,Hu Xiyuan,Peng Silong,et al.Single color image dehazing using sparse priors[C]//IEEE International Conference on Image Processing,2010:3593-3596.
[6]Zhu Qingsong,Mai Jiaming,Shao Ling.A fast single image haze removal algorithm using color attenuation prior[J].IEEE Transactions on Image Processing,2015,24(11):3522-3532.
[7]He K,Sun J,Tang X.Single image haze removal using dark channel prior[C]//IEEE Conference on Computer Vision and Pattern Recognition,2009:1956-1963.
[8]He K,Sun J,Tang X O,et al.Guided image filtering[C]//Proceedings of the 11th European Conference on Computer Vision,Heraklion,2010:1-14.
[9]苏晋鹏,陈恩俊,景嘉帅,等.基于阈值分割的暗原色先验图像去雾方法[J].计算机工程与应用,2017,53(3):205-210.
[10]Meng G,Wang Y,Duan J,et al.Efficient image dehazing with boundary constraint and contextual regularization[C]//IEEE International Conference on Computer Vision,2014:617-624.
[11]Tang K,Yang J,Wang J.Investigating haze-relevant features in a learning framework for image dehazing[C]//IEEE Conference on Computer Vision and Pattern Recognition,2014:2995-3002.
[12]麦嘉铭,王美华,梁云,等.特征学习的单幅图像去雾算法[J].中国图象图形学报,2016,21(4):464-474.
[13]Cai B,Xu X,Jia K,et al.DehazeNet:an end-to-end system for single image haze removal[J].IEEE Transactions on Image Processing,2016,25(11):5187-5198.
[14]Lin H Y,Lin C J.Using a hybrid of fuzzy theory and neural network filter for single image dehazing[J].Applied Intelligence,2017,47(4):1099-1114.
[15]Eigen D,Krishnan D,Fergus R.Restoring an image taken through a window covered with dirt or rain[C]//IEEE International Conference on Computer Vision,2013:633-640.
[16]刘万军,赵庆国.基于颜色饱和度的快速图像去雾研究[J].计算机工程与应用,2017,53(8):209-215.
[17]Nayar S K,Narasimhan S G.Vision in bad weather[C]//IEEE International Conference on Computer Vision,1999:820.
[18]李策,赵新宇,肖利梅,等.生成对抗映射网络下的图像多层感知去雾算法[J].计算机辅助设计与图形学学报,2017,29(10):1835-1843.
[19]Goodfellow I,Warde-farley D,Mirza M,et al.Maxout networks[C]//Proceedings of the 30th International Conference on Machine Learning,2013:1319-1327.
[20]Wu Y,Zhao H,Zhang L.Image denoising with rectified linear units[C]//International Conference on Neural Information Processing,Cham,2014:142-149.
[21]Wang W,Yuan X,Wu X,et al.Fast image dehazing method based on linear transformation[J].IEEE Transactions on Multimedia,2017,19(6):1142-1155.
[22]Scharstein D,Szeliski R.A taxonomy and evaluation of dense two-frame stereo correspondence algorithms[J].International Journal of Computer Vision,2002,47:7-42.
[23]Scharstein D,Szeliski R.High-accuracy stereo depth maps using structured light[C]//IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2003:195-202.